© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 107395
    Prev
    Next
    INDEX
    Explanations

    ARD campaign violations

    np_acts-logits-general · gemini-2.5-flash-lite

    resolving uncertainty or providing safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     đầu
    0.55
    ﯽ
    0.54
     луч
    0.51
    乙方
    0.50
     چنین
    0.50
    flop
    0.46
    ။
    0.46
    ني
    0.46
     তাছাড়া
    0.46
     solución
    0.46
    POSITIVE LOGITS
    arus
    0.57
    arik
    0.52
    metto
    0.48
    PS
    0.48
    ARD
    0.48
    ard
    0.46
    Ā
    0.46
    Ard
    0.46
    ardu
    0.46
    us
    0.45
    Activations Density 0.001%

    No Known Activations